Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark it destructive/open-world/non-idempotent, but the description adds substantial behavior beyond them: reviseScheduled atomically cancels a not-yet-started schedule and creates an unapproved draft without sending; approval binds the current web draft and prepared audience; permission/domain/frequency checks re-run at delivery; queued/scheduled is not delivered; accepted email cannot be recalled; and stable requestId makes retries idempotent. That is rich, non-redundant disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but mostly front-loaded: routing guidance first, then per-action behavior, then constraints. Some sentences are run-on (the reviseScheduled clause, the stacked 'approve/schedule... or send a test... or cancel' list), but given the multi-action complexity, little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex four-action, nested-payload tool with no output schema, the description covers the full lifecycle an agent needs: the human-review prerequisite, what each action does, idempotency handling, delivery-time re-checks, and irreversibility. Nothing essential to correct invocation appears missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the payload is an opaque additionalProperties object, so the description carries real weight: it maps each action to its required fields (campaignId, expectedRevision, requestId, scheduledAtMs, reviewHash) and explains that requestId makes a retried approval read back the recorded one. This adds meaning well past the generic payload description, though coverage of every field is not exhaustive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (email campaigns to your own list/network, newsletters, recurring mailings) and enumerates the actual operations (reviseScheduled, approve, test, cancel), clarifying that despite the 'send' name it governs approval/scheduling rather than immediate sending. It distinguishes itself from send_invitations and make_announcement by naming them. It never gives one crisp top-level verb+scope sentence, which keeps it just below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing: 'for your own list/network... use send_invitations to invite new people to one event, and make_announcement to message people already on an event's guest list.' It also prescribes a workflow (inspect review first, then approve/test/cancel) and references a guide resource. When-to-use and alternatives are both spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.